Towards Fair Graph Federated Learning via Incentive Mechanisms

TL;DR

This paper proposes a novel incentive mechanism for graph federated learning that promotes fairness and accuracy by considering agent contributions and heterogeneity, addressing issues of malicious and delayed agents.

Contribution

It introduces a new incentive mechanism tailored for graph federated learning, incorporating gradient and graph diversity, and employs motif prototypes to improve fairness and accuracy.

Findings

Achieves the best trade-off between accuracy and fairness.

Enhances global model aggregation with motif prototypes.

Outperforms existing methods in fairness and payoff distribution.

Abstract

Graph federated learning (FL) has emerged as a pivotal paradigm enabling multiple agents to collaboratively train a graph model while preserving local data privacy. Yet, current efforts overlook a key issue: agents are self-interested and would hesitant to share data without fair and satisfactory incentives. This paper is the first endeavor to address this issue by studying the incentive mechanism for graph federated learning. We identify a unique phenomenon in graph federated learning: the presence of agents posing potential harm to the federation and agents contributing with delays. This stands in contrast to previous FL incentive mechanisms that assume all agents contribute positively and in a timely manner. In view of this, this paper presents a novel incentive mechanism tailored for fair graph federated learning, integrating incentives derived from both model gradient and payoff. To achieve this, we first introduce an agent valuation function aimed at quantifying agent contributions through the introduction of two criteria: gradient alignment and graph diversity. Moreover, due to the high heterogeneity in graph federated learning, striking a balance between accuracy and fairness becomes particularly crucial. We introduce motif prototypes to enhance accuracy, communicated between the server and agents, enhancing global model aggregation and aiding agents in local model optimization. Extensive experiments show that our model achieves the best trade-off between accuracy and the fairness of model gradient, as well as superior payoff fairness.